Depth estimation with neural network, and learning on RGBD images
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.ipynb_checkpoints fuck May 23, 2016
latex Create commute.tex Apr 21, 2017
presentation Add files via upload Sep 20, 2017
resources fuck May 23, 2016
train Create README.md Jun 9, 2016
.gitignore fuck May 23, 2016
LICENSE Create LICENSE Sep 27, 2018
README.md
cifar2im.py
neural_net.py fuck May 23, 2016
packrgbd.py
rgbd.py fuck May 23, 2016
tryhere.ipynb fuck May 23, 2016

README.md

Estimated Depth Map Helps Image Classification

Yihui He, Xi'an Jiaotong University

RGBD dataset estimated depth classification

if you find our work helpful in your research, please consider citing:

@article{estimated2017he,
  title={Estimated Depth Map Helps Image Classification},
  author={He, Yihui},
  journal={arXiv preprint arXiv:1709.07077},
  year={2017}
}

how to test

  1. you can run tryhere.ipynb to test performance on RGBD and RGB images.
  2. you can do depth estimation in train/ folder

Approach

  1. train a mapping map RGB to depth
  2. convert cifar10 to images
  3. convert RGBD to cifar10 format
  4. train neural network on RGBD dataset

download

dcnf-fcsp
RGBD CIFAR-10

External Links

all dataset descriptions
a good one